Elan Rosenfeld

Hi! I'm a PhD student in the Machine Learning Department at CMU where I am fortunate to be advised by Pradeep Ravikumar and Andrej Risteski. I graduated from CMU with degrees in Computer Science and Statistics & Machine Learning. Before entering grad school I spent two years as a software engineer at Google NYC where I worked on Search Infrastructure and Machine Intelligence.

I'm broadly interested in theoretical foundations of machine learning; in particular, I focus on robustness, representation learning, and generalization under distribution shift. I work to develop formal models which allow for principled analyses of these tasks, with the eventual goal of devising new approaches to solving failure modes of existing methods.

Research/Mentorship Opportunities: I am always happy to discuss new research directions; if you're a student at CMU interested in working on domain adaptation / generalization, representation learning, or robust ML more generally, reach out to me! I am also available to give advice and feedback for those who are applying to undergraduate or graduate programs in computer science. If you are applying for a PhD in CMU SCS, I encourage you to sign up to receive feedback through the Graduate Application Support Program.

You can reach me at [firstname] at cmu.edu

[CV] [Semantic Scholar] [Google Scholar]

Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization

Elan Rosenfeld, Pradeep Ravikumar, Andrej Risteski

Conference Publications:

Iterative Feature Matching: Toward Provable Domain Generalization
with Logarithmic Environments

NeurIPS 2022

Yining Chen, Elan Rosenfeld, Mark Sellke, Tengyu Ma, Andrej Risteski

Analyzing and Improving the Optimization Landscape of
Noise-Contrastive Estimation

ICLR 2022

Bingbin Liu, Elan Rosenfeld, Pradeep Ravikumar, Andrej Risteski
[arXiv] [blog post]

Deep Attentive Variational Inference
ICLR 2022

Ifigeneia Apostolopoulou, Ian Char, Elan Rosenfeld, Artur Dubrawski

An Online Learning Approach to Interpolation and Extrapolation
in Domain Generalization


Elan Rosenfeld, Pradeep Ravikumar, Andrej Risteski

The Risks of Invariant Risk Minimization
ICLR 2021

Elan Rosenfeld, Pradeep Ravikumar, Andrej Risteski
[arXiv] [poster] [CMU AI Seminar Talk] [2 minute spotlight presentation]

Certified Robustness to Label-Flipping Attacks via Randomized Smoothing
ICML 2020

Elan Rosenfeld, Ezra Winston, Pradeep Ravikumar, Zico Kolter
[arXiv] [code (.zip)] [blog post] [virtual poster/presentation]

Certified Adversarial Robustness via Randomized Smoothing
ICML 2019

Jeremy Cohen, Elan Rosenfeld, Zico Kolter
[arXiv] [code] [ICML talk] [Zico's Simons talk]

Workshops and Manuscripts:

APE: Aligning Pretrained Encoders to Quickly Learn Aligned Multimodal Representations
NeurIPS 2022 Workshop: Has It Trained Yet?

Elan Rosenfeld, Preetum Nakkiran, Hadi Pouransari, Oncel Tuzel, Fartash Faghri

Self-Reflective Variational Autoencoder
ICLR 2021 Workshop: Hardware Aware Efficient Training

Ifigeneia Apostolopoulou, Elan Rosenfeld, Artur Dubrawski
[arXiv] [poster] [short presentation]

Human-Usable Password Schemas: Beyond Information-Theoretic Security
CMU Senior Thesis
Awarded “Exemplary Senior Honors Thesis”

Elan Rosenfeld, Santosh Vempala, Manuel Blum
[arXiv] [poster]